Paul Wright

@KumoLiu I had another look at the test code you gave and saw it sets the CUDA_VISIBLE_DEVICES environment variable. When I set that, it works, and says "Found 1 GPUs...

> Hi @pwrightkcl, perhaps the issue is due to the `DataAnalyzer` can not work in multi-node, could you please try `AutoRunner` without data analyze? Thank you for the suggestion. I'm...

@ericspod advised me to put my script inside a `main` function then add `freeze_support()` at the top of that, as suggested in the error message. That appears to have fixed...

@kretes Sorry for slow response (just got back from leave). Just to confirm, the solution for me was to put my code in a `main()` function and to add `freeze_support()`...

Here's what the log file looked like as it was getting truncated. You can see the two log lines prior to the first reg_aladin line are removed. There should be...

Here is some actual code. I'm afraid it's long: there's a wrapper script containing the command with the redirection to the log file, that command generates a third script and...

I haven't examined it in detail since I did the testing above. I'd still prefer if this didn't happen, but like you I have no idea why it does, or...

I moved my data to an EXT4 filesystem on the same system, and this problem does not occur. I restarted Docker Desktop, and the containers ran as before, whether started...

After leaving overnight, the jobs got past the error with `build-essential` installed. I still see the following deprecation warning following a mention of torch.compile: ```text 2024-05-28 17:06:21.793990: This split has...

@bruniss Do you mean a onehot encoding? That would have a separate mask for "all ventricle" and "all blood". I think I tried that early on but will review and...